Terminal & Shell

Bridge local agent — connects your AI tools to Jerico

fhcode（飞虹 Code）— 终端 AI 编程智能体：多模型路由（DeepSeek/通义/Ollama/OpenAI）、企业级 RBAC 审计、全自动 SWE Agent、支持离线私有化。源代码 Apache-2.0 开源自托管，企业版增值能力（激活码、完全私有化部署与商业支持）采用商业授权双轨模式。

Open-source agent orchestration layer — the AI company OS. Local model agent engine (GGUF/Ollama/llama-server), HuggingFace model browser, MCP integrations (Slack, Gmail, Stripe, 15+), agent scheduling (cron), business roles (CMO, CFO, EA). GUI dashboard,

本地优先的多 Agent 协作与自动开发工作区，集成任务编排、记忆上下文、MCP/Skill、TestAgent、Git、飞书、知识库和终端

The wuapi command line: log in from the browser, link a WhatsApp number through a link the person opens (QR or pairing code), run your app with the key, send messages, set up the MCP server and call every endpoint of the wuapi API from your terminal or yo

Computer-use MCP for Windows 10/11: 32 tools — screenshot, UIA, Chrome CDP, type/click/scroll, VBA.

This package will help us to get equity/index details and historical data from National Stock Exchange of India.

Model Context Protocol server for tmux, built on libtmux.

The security-native AI coding agent. Six Sec-Test security personas, compliance-first /scraper, a business documents & research suite, and multi-agent Compose orchestration — spec-driven workflow engines in one terminal-first CLI.

AI-native bash interpreter in TypeScript — a sandboxed, in-process POSIX shell engine for AI agents, with 110+ builtins, WASM Python/JS/SQLite runtimes, fork-speculation, an MCP server, and an agent terminal bridge.

The ShipBash command line: manage the journeys and hooks ShipBash tests your web app or CLI with, run them, read the results and pull evidence, from a terminal or a coding agent.

Vue 3 terminal UI components and renderers for browser DOM, CLI stdout, logs, markdown transcripts, and agent consoles

payware A2A payments API for merchants, ISVs and payment institutions

InnerWarden Community: open-source guardrail for AI coding agents. Screens the shell commands and MCP/tool calls your agent runs and returns allow / review / deny, before it runs.

Open-source autonomous AI coding agent CLI & native MCP client (free Claude Code alternative). Desktop & browser automation, workspace tools, 5-layer guardrails, Docker sandbox, and custom OpenAI/NVIDIA NIM providers.

Zero-dependency context & token optimizer for Claude Code, Codex CLI, and Google Antigravity. Cuts terminal output by up to 96.4% to prevent context window exhaustion.

MCP server and CLI bridging AI coding agents (Cursor, Claude Code, Codex, Kiro, Antigravity, Claude Desktop) to the Customaise Chrome extension. 19 tools: UserScripts, AgentScripts, WebMCP calls with HITL consent, visual DOM targeting, tab control. Drive

Comprehensive security sanitization library for Model Context Protocol (MCP) servers with trusted security libraries

Mobile remote code editor & AI agent terminal companion

Policy-aware AI permission reviewer for OpenCode V1 and V2: auto-approves routine agent tool calls, denies risky ones with feedback, and escalates the rest to you